Problem in reading mfcc file

[Nikul Prajapati]

Hi,

I have installed latest version of sphinx3 and sphinxbase from the repository.
When I am giving absolute path of mfcc file to sphinx then sphinx treat it as
a relative path and insert ./ at the start of the path string. So sphinx
is always failed to read mfcc file.

eg:

-utt /home/asr/demo6sep/feats/$filename.mfc

what could be the problem here?

Error log( Main part of error is last 5-6 lines)

INFO: cmd_ln.c(691): Parsing command line:
/home/asr/tools/sphinx_3_8_latest/sphinx3/bin/sphinx3_decode \
    -hmm /home/asr/demo6sep/models/hmm \
    -lm /home/asr/demo6sep/models/lm/district/district.lm.DMP \
    -mode fwdflat \
    -dict /home/asr/demo6sep/models/lm/dictionary110503.dic \
    -fdict /home/asr/demo6sep/models/lm/test.filler \
    -ctlcount 1 \
    -utt /home/asr/demo6sep/feats/temp_asr.mfc \
    -logfn /home/asr/demo6sep/LogOutfiles/temp_asr.log.txt \
    -hyp /home/asr/demo6sep/LogOutfiles/temp_asr.out.txt \
    -hypseg /home/asr/demo6sep/LogOutfiles/hypseg.txt

Current configuration:
[NAME]          [DEFLT]     [VALUE]
-adchdr         0       0
-adcin          no      no
-agc            none        none
-agcthresh      2.0     2.000000e+00
-alpha          0.97        9.700000e-01
-backtrace      yes     yes
-beam           1.0e-55     1.000000e-55
-bestpath       no      no
-bestpathlw             0.000000e+00
-bestscoredir               
-bestsenscrdir              
-bghist         no      no
-bgonly         no      no
-bptbldir               
-bptblsize      32768       32768
-build_outdirs      yes     yes
-cb2mllr        .1cls.      .1cls.
-cepdir         .       .
-cepext         .mfc        .mfc
-ceplen         13      13
-ci_pbeam       1e-80       1.000000e-80
-cmn            current     current
-cmninit        8.0     8.0
-cond_ds        no      no
-ctl                    
-ctlcount       1000000000  1
-ctloffset      0       0
-ctl_lm                 
-ctl_mllr               
-dagfudge       2       2
-debug                  0
-dict                   /home/asr/demo6sep/models/lm/dictionary110503.dic
-dist_ds        no      no
-dither         no      no
-doublebw       no      no
-ds         1       1
-epl            3       3
-fdict                  /home/asr/demo6sep/models/lm/test.filler
-feat           1s_c_d_dd   1s_c_d_dd
-featparams             
-fillpen                
-fillprob       0.1     1.000000e-01
-frate          100     100
-fsg                    
-fsgusealtpron      yes     yes
-fsgusefiller       yes     yes
-gs                 
-gs4gs          yes     yes
-hmm                    /home/asr/demo6sep/models/hmm
-hmmdump        no      no
-hmmdumpef      200000000   200000000
-hmmdumpsf      200000000   200000000
-hmmhistbinsize     5000        5000
-hyp                    /home/asr/demo6sep/LogOutfiles/temp_asr.out.txt
-hypseg                 /home/asr/demo6sep/LogOutfiles/hypseg.txt
-hypsegscore_unscale    yes     yes
-inlatdir               
-inlatwin       50      50
-input_endian       little      little
-kdmaxbbi       -1      -1
-kdmaxdepth     0       0
-kdtree                 
-latcompress        yes     yes
-latext         lat.gz      lat.gz
-lda                    
-ldadim         0       0
-lextreedump        0       0
-lifter         0       0
-lm                 /home/asr/demo6sep/models/lm/district/district.lm.DMP
-lmctlfn                
-lmdumpdir              
-lmname                 
-log3table      yes     yes
-logbase        1.0003      1.000300e+00
-logfn                  /home/asr/demo6sep/LogOutfiles/temp_asr.log.txt
-logspec        no      no
-lowerf         133.33334   1.333333e+02
-lts_mismatch       no      no
-lw         9.5     9.500000e+00
-maxcdsenpf     100000      100000
-maxedge        2000000     2000000
-maxhistpf      100     100
-maxhmmpf       20000       20000
-maxlmop        100000000   100000000
-maxlpf         40000       40000
-maxppath       1000000     1000000
-maxwpf         20      20
-mdef                   
-mdef_fillers       no      no
-mean                   
-min_endfr      3       3
-mixw                   
-mixwfloor      0.0000001   1.000000e-07
-mllr                   
-mode           fwdtree     fwdflat
-nbest          200     200
-nbestdir               
-nbestext       nbest.gz    nbest.gz
-ncep           13      13
-nfft           512     512
-nfilt          40      40
-Nlextree       3       3
-Nstalextree        25      25
-op_mode        -1      -1
-outlatdir              
-outlatfmt      s3      s3
-pbeam          1.0e-50     1.000000e-50
-pheurtype      0       0
-phonepen       1.0     1.000000e+00
-phsegdir               
-pl_beam        1.0e-80     1.000000e-80
-pl_window      1       1
-ppathdebug     no      no
-ptranskip      0       0
-remove_dc      no      no
-round_filters      yes     yes
-samprate       16000       1.600000e+04
-seed           -1      -1
-sendump                
-senmgau        .cont.      .cont.
-silprob        0.1     1.000000e-01
-smoothspec     no      no
-subvq                  
-subvqbeam      3.0e-3      3.000000e-03
-svq4svq        no      no
-svspec                 
-tighten_factor     0.5     5.000000e-01
-tmat                   
-tmatfloor      0.0001      1.000000e-04
-topn           4       4
-topn_beam      0       0
-tracewhmm              
-transform      legacy      legacy
-treeugprob     yes     yes
-ugonly         no      no
-unit_area      yes     yes
-upperf         6855.4976   6.855498e+03
-utt                    /home/asr/demo6sep/feats/temp_asr.mfc
-uw         0.7     7.000000e-01
-var                    
-varfloor       0.0001      1.000000e-04
-varnorm        no      no
-verbose        no      no
-vqeval         3       3
-warp_params                
-warp_type      inverse_linear  inverse_linear
-wbeam          1.0e-35     1.000000e-35
-wend_beam      1.0e-80     1.000000e-80
-wip            0.7     7.000000e-01
-wlen           0.025625    2.562500e-02
-worddumpef     200000000   200000000
-worddumpsf     200000000   200000000

INFO: kbcore.c(442): Begin Initialization of Core Models:
ERROR: "cmd_ln.c", line 787: Cannot open configuration file /home/asr/demo6sep/models/hmm/feat.params for reading
INFO: kbcore.c(462): Parsed model-specific feature parameters from /home/asr/demo6sep/models/hmm/feat.params
INFO:   Initialization of the log add table
INFO:   Log-Add table size = 29356 x 2 >> 0
INFO:   
INFO: feat.c(684): Initializing feature stream to type: '1s_c_d_dd', ceplen=13, CMN='current', VARNORM='no', AGC='none'
INFO: cmn.c(142): mean[0]= 12.00, mean[1..12]= 0.0
INFO: kbcore.c(489): .cont.
INFO:   Initialization of feat_t, report:
INFO:   Feature type         = 1s_c_d_dd
INFO:   Cepstral size        = 13
INFO:   Number of streams    = 1
INFO:   Vector size of stream[0]: 39
INFO:   Number of subvectors = 0
INFO:   Whether CMN is used  = 1
INFO:   Whether AGC is used  = 0
INFO:   Whether variance is normalized = 0
INFO:   
INFO:   Reading HMM in Sphinx 3 Model format
INFO:   Model Definition File: /home/asr/demo6sep/models/hmm/mdef
INFO:   Mean File: /home/asr/demo6sep/models/hmm/means
INFO:   Variance File: /home/asr/demo6sep/models/hmm/variances
INFO:   Mixture Weight File: /home/asr/demo6sep/models/hmm/mixture_weights
INFO:   Transition Matrices File: /home/asr/demo6sep/models/hmm/transition_matrices
INFO: mdef.c(683): Reading model definition: /home/asr/demo6sep/models/hmm/mdef
INFO:   Initialization of mdef_t, report:
INFO:   76 CI-phone, 23730 CD-phone, 3 emitstate/phone, 228 CI-sen, 728 Sen, 977 Sen-Seq
INFO:   
INFO: kbcore.c(299): Using optimized GMM computation for Continuous HMM, -topn will be ignored
INFO: cont_mgau.c(163): Reading mixture gaussian file '/home/asr/demo6sep/models/hmm/means'
INFO: cont_mgau.c(422): 728 mixture Gaussians, 8 components, 1 streams, veclen 39
INFO: cont_mgau.c(163): Reading mixture gaussian file '/home/asr/demo6sep/models/hmm/variances'
INFO: cont_mgau.c(422): 728 mixture Gaussians, 8 components, 1 streams, veclen 39
INFO: cont_mgau.c(523): Reading mixture weights file '/home/asr/demo6sep/models/hmm/mixture_weights'
INFO: cont_mgau.c(678): Read 728 x 8 mixture weights
INFO: cont_mgau.c(706): Removing uninitialized Gaussian densities
WARNING: "cont_mgau.c", line 780: 17 densities removed (0 mixtures removed entirely)
INFO: cont_mgau.c(796): Applying variance floor
INFO: cont_mgau.c(814): 186 variance values floored
INFO: cont_mgau.c(862): Precomputing Mahalanobis distance invariants
INFO: tmat.c(119): Reading HMM transition probability matrices: /home/asr/demo6sep/models/hmm/transition_matrices
INFO:   Initialization of tmat_t, report:
INFO:   Read 76 transition matrices of size 3x4
INFO:   
INFO: dict.c(385): Reading main dictionary: /home/asr/demo6sep/models/lm/dictionary110503.dic
ERROR: "dict.c", line 265: Line 90: Phone 'pp' is mising in the acoustic model; word '_56' ignored
ERROR: "dict.c", line 265: Line 91: Phone 'pp' is mising in the acoustic model; word '_56(2)' ignored
ERROR: "dict.c", line 265: Line 145: Phone 'ar' is mising in the acoustic model; word '_78(2)' ignored
ERROR: "dict.c", line 265: Line 204: Phone 'mm' is mising in the acoustic model; word 'amalxanera(2)' ignored
ERROR: "dict.c", line 265: Line 339: Phone 'pp' is mising in the acoustic model; word 'dxappaa' ignored
ERROR: "dict.c", line 265: Line 416: Phone 'oo' is mising in the acoustic model; word 'ho(2)' ignored
ERROR: "dict.c", line 265: Line 471: Phone 'dd' is mising in the acoustic model; word 'kadduu' ignored
ERROR: "dict.c", line 265: Line 631: Phone 'oo' is mising in the acoustic model; word 'no(2)' ignored
ERROR: "dict.c", line 265: Line 891: Phone 'oo' is mising in the acoustic model; word 'wrong(3)' ignored
INFO: dict.c(388): 888 words read
INFO: dict.c(393): Reading filler dictionary: /home/asr/demo6sep/models/lm/test.filler
INFO: dict.c(396): 3 words read
INFO: dict.c(429): Added 0 fillers from mdef file
INFO:   Initialization of dict_t, report:
INFO:   No of CI phone: 0
INFO:   Max word: 4996
INFO:   No of word: 891
INFO:   
INFO: lm.c(612): LM read('/home/asr/demo6sep/models/lm/district/district.lm.DMP', lw= 9.50, wip= 0.70, uw= 0.70)
INFO: lm.c(614): Reading LM file /home/asr/demo6sep/models/lm/district/district.lm.DMP (LM name "default")
INFO: lm_3g_dmp.c(631): Reading LM in 16 bits format
INFO: lm_3g_dmp.c(687): Read       33 unigrams [in memory]
INFO: lm_3g_dmp.c(760):       62 bigrams [on disk]
INFO: lm_3g_dmp.c(833):       91 bigrams [on disk]
INFO: lm_3g_dmp.c(903):        4 bigram prob entries
INFO: lm_3g_dmp.c(937):        5 trigram bowt entries
INFO: lm_3g_dmp.c(968):        3 trigram prob entries
INFO: lm_3g_dmp.c(999):        1 trigram segtable entries (512 segsize)
INFO: lm_3g_dmp.c(1054):       33 word strings
INFO: lm.c(710): The LM routine is operating at 16 bits mode
INFO:   Initialization of fillpen_t, report:
INFO:   Language weight =9.500000 
INFO:   Word Insertion Penalty =0.700000 
INFO:   Silence probability =0.100000 
INFO:   Filler probability =0.100000 
INFO:   
INFO: dict2pid.c(600): Building PID tables for dictionary
INFO:   Initialization of dict2pid_t, report:
INFO:   Dict2pid is in composite triphone mode
INFO:   542 composite states; 221 composite sseq
INFO:   
INFO: kbcore.c(635): Inside kbcore: Verifying models consistency ...... 
INFO: kbcore.c(657): End of Initialization of Core Models:
INFO:   Initialization of beam_t, report:
INFO:   Parameters used in Beam Pruning of Viterbi Search:
INFO:   Beam=-422203
INFO:   PBeam=-383821
INFO:   WBeam=-268675 (Skip=0)
INFO:   WEndBeam=-614114 
INFO:   No of CI Phone assumed=76 
INFO:   
INFO:   Initialization of fast_gmm_t, report:
INFO:   Parameters used in Fast GMM computation:
INFO:      Frame-level: Down Sampling Ratio 1, Conditional Down Sampling? 0, Distance-based Down Sampling? 0
INFO:        GMM-level: CI phone beam -614114. MAX CD 100000
INFO:   Gaussian-level: GS map would be used for Gaussian Selection? =1, SVQ would be used as Gaussian Score? =0 SubVQ Beam -19366
INFO:   
INFO:   Initialization of pl_t, report:
INFO:   Parameters used in phoneme lookahead:
INFO:   Phoneme look-ahead        type = 0
INFO:   Phoneme look-ahead beam   size = -614114
INFO:   No of CI Phones assumed=76 
INFO:   
INFO:   Initialization of ascr_t, report:
INFO:   No. of CI senone =228 
INFO:   No. of senone = 728
INFO:   No. of composite senone = 542
INFO:   No. of senone sequence = 977
INFO:   No. of composite senone sequence=221 
INFO:   Parameters used in phoneme lookahead:
INFO:   Phoneme lookahead window = 1
INFO:   
ERROR: "kb.c", line 172: fopen(/home/asr/demo6sep/LogOutfiles/hypseg.txt,w) failed; use FWDXCT: from std logfile
INFO: kb.c(308): SEARCH MODE INDEX 3
INFO: srch.c(376): Search Initialization. 
INFO: srch_flat_fwd.c(205): Initialization
INFO: ctxt_table.c(256): Building within-word triphones
INFO: ctxt_table.c(288): 324 within-word triphone instances mapped to CI-phones
INFO: ctxt_table.c(310): Building cross-word triphones
INFO: ctxt_table.c(371): 3168 cross-word triphones mapped to CI-phones
INFO:   Initialization of srch_t, report:
INFO:   Operation Mode = 3, Operation Name = fwdflat
INFO:   
INFO: utt.c(74): Processing: temp_asr.mfc_00000000
INFO: feat.c(1176): At directory .
[b]INFO: feat.c(993): Reading mfc file: './/home/asr/demo6sep/feats/temp_asr.mfc'[0..-1]
SYSTEM_ERROR: "pio.c", line 450: stat(.//home/asr/demo6sep/feats/temp_asr.mfc) failed; retrying...
; No such file or directory
ERROR: "feat.c", line 1002: Failed to open file './/home/asr/demo6sep/feats/temp_asr.mfc' for reading: No such file or directory
FATAL_ERROR: "utt.c", line 120: Cannot read file /home/asr/demo6sep/feats/temp_asr.mfc. Forced exit[/b]

[Nickolay V. Shmyrev]

It tries to load the file relative the the folder configured with -cepdir
option. In your case it tries to load the file from the current folder. You
need to specify relative path according to your current folder or you need to
configure the base path with the -cepdir option.

[Nikul Prajapati]

Yes that problem has been solved by setting -cepdir to root directory.

But still there is another problem.
Sphinx is failed to read mfc file, when mfc file name is long.Here below is
example of long mfc file name.

/home/asr/demo6sep/feats/000524_1_1_5-1-2012-23-51-43_asr.mfc

Sphinx giving below error when i am supplying above mfc file path. With the
short mfc file name there is no any problem.
Please, let me know what the problem is?

Error log

INFO: utt.c(74): Processing: 000524_1_1_5-1-2012-23-51-43_asr.mfc_00000000
INFO: feat.c(1176): At directory 
INFO: feat.c(993): Reading mfc file: '//home/asr/demo6sep/feats/000524_1_1_5-1-.mfc'[0..-1]
SYSTEM_ERROR: "pio.c", line 450: stat(//home/asr/demo6sep/feats/000524_1_1_5-1-.mfc) failed; retrying...
; No such file or directory
ERROR: "feat.c", line 1002: Failed to open file '//home/asr/demo6sep/feats/000524_1_1_5-1-.mfc' for reading: No such file or directory
FATAL_ERROR: "utt.c", line 120: Cannot read file /home/asr/demo6sep/feats/000524_1_1_5-1-. Forced exit

Thanks,

[Nickolay V. Shmyrev]

Please, let me know what the problem is?

The problem is that file name is too long.

[Chandan G M]

hi...
iam doing this project for semicontinuos so i have an4,pocketsphinx,sphinxbase and sphinxtrain.
The problem is after data (an4) got set up, i got sphinxtrain.cfg and feat.params in my etc file.Then i modified sphinxtrain.cfg.(i used pocket sphinx). While running the the next step
"python ../sphinxtrain/scripts/sphinxtrain run".iam getting output as feature extraction is done. but im not getting mfcc feature in feat file, simply it creates feat file. It will go to the next step(verify_all.pl),
there im getting "warrning:error 'D:spnx/an4/etc/an4_train.fileids the feature file D:spnx/an4/feat/1.mfc doesnot exist or empty...what is the error in this?
Thanks...

[Chandan G M]

These are my an4 files